Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4396 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.9688. Min Act: -0.1700
Data Index: 7805845 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.9063. Min Act: -0.1700
Data Index: 7272321 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8751. Min Act: -0.1700
Data Index: 1584011 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8751. Min Act: -0.1700
Data Index: 8621634 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8126. Min Act: -0.1700
Data Index: 3862596 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8126. Min Act: -0.1700
Data Index: 5505818 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8126. Min Act: -0.1700
Data Index: 5670854 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.8438. Min Act: -0.1700
Data Index: 4482996 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.7501. Min Act: -0.1700
Data Index: 5471229 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6876. Min Act: -0.1700
Data Index: 6844518 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6876. Min Act: -0.1700
Data Index: 1274878 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6876. Min Act: -0.1700
Data Index: 555330 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6563. Min Act: -0.1700
Data Index: 1673607 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6563. Min Act: -0.1700
Data Index: 5009588 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6563. Min Act: -0.1700
Data Index: 7931811 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.5938. Min Act: -0.1700
Data Index: 2480178 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6251. Min Act: -0.1700
Data Index: 4120973 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6251. Min Act: -0.1700
Data Index: 6960590 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6251. Min Act: -0.1700
Data Index: 2082341 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9688. Min Range: -4.9688
Max Act: 4.6251. Min Act: -0.1700
Data Index: 3702130 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19